Graph Learning





Graphs provide a natural way of representing complex data. In rrecent years, graph anlytics has proliferated rapidly, and it has useful applications across a wide range of fields, such as social science, computer science, biology and archaeology. However, graph analytics is often computationally expensive and technically challenging. Regardless of how different analytical systems may handle graph data, the need to capture semantics remains. Can the accuracy of graph analytics be improved by leveraging topological structure in their representations?

Updated:  1 June 2019/Responsible Officer:  Dean, CECS/Page Contact:  CECS Marketing